Autonomous Vehicle Maneuver Planning for Lane-Blocking Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face a challenge in balancing assertive maneuvers with safety, as they tend to be overly cautious to avoid collisions, leading to delays and passenger discomfort, while more assertive actions can be dangerous if human drivers do not react in time.
Innovation Solution
The system predicts the response of other vehicles to potential assertive actions by the autonomous vehicle, such as making turns or passing, and adjusts its behavior to cancel the action if necessary, ensuring safety without causing collisions, by using behavior models and accommodation protocols to determine the feasibility of completing actions like making turns or passing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles operate with less assertive behaviors to prioritize safety, then collision risk is reduced, but operational efficiency and passenger satisfaction deteriorate due to delays
Solution Approach 1:
The system performs preliminary actions by communicating maneuver intentions to other vehicles in advance. The autonomous vehicle transmits data about its planned maneuvers (turns, lane changes, passing) to nearby vehicles, allowing them to prepare appropriate responsive actions. This advance notice enables the autonomous vehicle to execute more assertive maneuvers while maintaining safety, as other drivers have time to react appropriately.
2Productivity
If autonomous vehicles make more assertive maneuvers to improve operational efficiency, then productivity increases, but safety deteriorates due to increased collision risk
Solution Approach 1:
The system implements feedback by monitoring whether other vehicles are taking the predicted responsive actions. The autonomous vehicle's processors continuously determine whether nearby vehicles are reacting as expected to the communicated maneuver intentions. This feedback loop allows the system to adjust its assertiveness dynamically - proceeding with assertive maneuvers when feedback confirms safety, and aborting when feedback indicates potential danger.
3Reliability
If autonomous vehicles cancel maneuvers to avoid collisions, then safety is maintained, but operational delays increase
Solution Approach 1:
By communicating maneuver intentions in advance to other vehicles, the system eliminates the need for last-minute cancellations. Other drivers receive early notice of upcoming maneuvers and can prepare appropriate responses, allowing the autonomous vehicle to execute its planned actions without sudden aborts or delays.
4Reliability
If autonomous vehicles wait for other vehicles to clear the path, then collision risk is reduced, but productivity decreases due to waiting time
Solution Approach 1:
Instead of passively waiting for other vehicles to clear the path, the system takes preliminary action by notifying them of the autonomous vehicle's intended maneuver. This allows the autonomous vehicle to proceed with its maneuver while other vehicles simultaneously adjust their positions, eliminating the need for the autonomous vehicle to wait idle.
Data Source
AI summary
A method and apparatus for controlling a first vehicle autonomously are disclosed. For instance, one or more processors may plan to maneuver the first vehicle to complete an action and predict that a second vehicle will take a particular responsive action. The first vehicle is then maneuvered towards completing the action in a way that would allow the first vehicle to cancel completing the action without causing a collision between the first vehicle and the second vehicle, and in order to indicate to the second vehicle or a driver of the second vehicle that the first vehicle is attempting to complete the action. Thereafter, when the first vehicle is determined to be able to take the action, the action is completed by controlling the first vehicle autonomously according to whether the second vehicle begins to take the particular responsive action.